从人类视频到机器人操作：基于人类中心数据的可扩展视觉-语言-动作学习综述
From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data
AI总结：
本文综述了如何将丰富的人类视频转化为视觉-语言-动作（VLA）模型的有效知识，分类了四种方法（潜在动作表示、预测世界模型、显式2D监督、显式3D重建），并指出了结构化非结构化视频、跨具身和视角的动作映射、以及评估协议设计三大挑战。
摘要：
近期在可泛化具身控制方面的进展由大规模预训练的视觉-语言-动作（VLA）模型驱动。然而，大多数现有方法依赖于大量机器人演示数据，这些数据获取成本高昂且与特定具身紧密耦合。相比之下，人类视频丰富且捕捉了丰富的交互，为真实世界操作提供了多样的语义和物理线索。然而，具身差异以及任务对齐标注的频繁缺失使得它们直接用于VLA模型具有挑战性。本综述提供了一个统一的视角，探讨如何将人类视频转化为VLA模型的有效知识。我们根据所提取的动作相关信息将现有方法分为四类：(i) 编码帧间变化的潜在动作表示；(ii) 预测未来帧的预测世界模型；(iii) 提取图像平面线索的显式2D监督；(iv) 恢复几何或运动的显式3D重建。除分类外，我们强调了该领域的三个关键开放挑战：将非结构化视频结构化为可训练的片段、在具身和视角异质性下将视频导出的监督接地到机器人可执行动作中，以及设计能更好预测真实世界部署性能和迁移效率的评估协议，从而为未来研究方向提供参考。论文和资源的精选列表见 https://github.com/AaronFengZY/HumanCentricToVLA-Survey。
英文摘要：
Recent progress in generalizable embodied control has been driven by large-scale pretraining of Vision-Language-Action (VLA) models. However, most existing approaches rely on large collections of robot demonstrations, which are costly to obtain and tightly coupled to specific embodiments. Human videos, by contrast, are abundant and capture rich interactions, providing diverse semantic and physical cues for real-world manipulation. Yet, embodiment differences and the frequent absence of task-aligned annotations make their direct use in VLA models challenging. This survey provides a unified view of how human videos are transformed into effective knowledge for VLA models. We categorize existing approaches into four classes based on the action-related information they derive: (i) latent action representations that encode inter-frame changes; (ii) predictive world models that forecast future frames; (iii) explicit 2D supervision that extracts image-plane cues; and (iv) explicit 3D reconstruction that recovers geometry or motion. Beyond this taxonomy, we highlight three key open challenges in this area: structuring unstructured videos into training-ready episodes, grounding video-derived supervision into robot-executable actions under embodiment and viewpoint heterogeneity, and designing evaluation protocols that better predict real-world deployment performance and transfer efficiency, thereby informing future research directions. A curated list of papers and resources is available at https://github.com/AaronFengZY/HumanCentricToVLA-Survey.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
